Triple

T19526883
Position Surface form Disambiguated ID Type / Status
Subject Johnny Clay E488542 entity
Predicate worksWith P398 FINISHED
Object Mike O’Reilly
Mike O’Reilly is a character associated with Johnny Clay, likely involved in criminal or heist-related activities in the same narrative.
 E1382347 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mike O’Reilly | Statement: [Johnny Clay, worksWith, Mike O’Reilly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mike O’Reilly
Context triple: [Johnny Clay, worksWith, Mike O’Reilly]
  • A. Bill O’Reilly
    Bill O’Reilly is an American conservative political commentator, author, and former long-time host of the Fox News program "The O’Reilly Factor."
  • B. Larry O’Reilly
    Larry O’Reilly is a film director best known for directing the short documentary "Crashing the Water Barrier."
  • C. John Batchelor
    John Batchelor is an Australian actor known for his work in film, television, and theatre.
  • D. Adam Boulton
    Adam Boulton is a British political journalist and broadcaster best known for his long tenure as Sky News’ political editor and presenter.
  • E. Dan Bongino
    Dan Bongino is a conservative political commentator, former Secret Service agent, and radio host known for his outspoken support of Donald Trump and frequent appearances on right-leaning media outlets.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mike O’Reilly
Triple: [Johnny Clay, worksWith, Mike O’Reilly]
Generated description
Mike O’Reilly is a character associated with Johnny Clay, likely involved in criminal or heist-related activities in the same narrative.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mike O’Reilly
Target entity description: Mike O’Reilly is a character associated with Johnny Clay, likely involved in criminal or heist-related activities in the same narrative.
  • A. Bill O’Reilly
    Bill O’Reilly is an American conservative political commentator, author, and former long-time host of the Fox News program "The O’Reilly Factor."
  • B. Larry O’Reilly
    Larry O’Reilly is a film director best known for directing the short documentary "Crashing the Water Barrier."
  • C. John Batchelor
    John Batchelor is an Australian actor known for his work in film, television, and theatre.
  • D. Adam Boulton
    Adam Boulton is a British political journalist and broadcaster best known for his long tenure as Sky News’ political editor and presenter.
  • E. Dan Bongino
    Dan Bongino is a conservative political commentator, former Secret Service agent, and radio host known for his outspoken support of Donald Trump and frequent appearances on right-leaning media outlets.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363c2660819093a6b9a444ca0ad4 completed April 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a074e75fec481909397b747891f9315 completed May 15, 2026, 4:48 p.m.
NEDg Description generation batch_6a0750d8e8688190aa096bd8853fee89 completed May 15, 2026, 4:59 p.m.
NED2 Entity disambiguation (via description) batch_6a075140b8708190aed4f54b072eacc7 completed May 15, 2026, 5 p.m.
Created at: April 10, 2026, 1:41 p.m.